Open ASR · AMI-Cleaned WER ↗English short-form; normalization unversioned
6.95% WERmicrosoft/azure-speech-06-2026
microsoftDiscovered Oct 17, 2026
microsoft/azure-speech-06-2026
25 languages · Decoder: LLM
Measured performance
All leaderboards ↗Benchmark results
Word error rate · lower is better
Open ASR · Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversioned
5.59% WERmicrosoft/azure-speech-06-2026
Open ASR · Gigaspeech-Cleaned WER ↗English short-form; normalization unversioned
7.26% WERmicrosoft/azure-speech-06-2026
Open ASR · LS Clean WER ↗English short-form; normalization unversioned
1.19% WERmicrosoft/azure-speech-06-2026
Open ASR · LS Other WER ↗English short-form; normalization unversioned
2.5% WERmicrosoft/azure-speech-06-2026
Open ASR · SPGISpeech WER ↗English short-form; normalization unversioned
2.31% WERmicrosoft/azure-speech-06-2026
Open ASR · Voice Arena Monsoon WER ↗English short-form; normalization unversioned
4.4% WERmicrosoft/azure-speech-06-2026
Open ASR · Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversioned
3.87% WERmicrosoft/azure-speech-06-2026
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- microsoft
- Modality
- Audio
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- First discovered
- Oct 17, 2026
Exact identities
- open-asr
microsoft%2Fazure-speech-06-2026
Sources
Updated Oct 17, 2026
More from microsoft
View all ↗microsoftListed 16 days ago
Microsoft AI: MAI-Voice-2.1-Flash
MAI-Voice-2.1-Flash is a low-latency text-to-speech model from Microsoft AI, optimized for real-time responsiveness. It produces natural, expressive speech across 23 languages, with human-like intonation,…
No reported score
No reported score
Price not listed
microsoftListed 16 days ago
Microsoft AI: MAI-Voice-2.1
MAI-Voice-2.1 is Microsoft AI's highest-fidelity, most expressive text-to-speech model. It produces natural, studio-grade speech across 23 languages, with detailed prosody, nuanced expressiveness, and…
No reported score
No reported score
Price not listed
microsoftListed Jul 23
Microsoft AI: MAI-Voice-2-Flash
MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24…
No reported score
No reported score
Price not listed
microsoftListed Jun 2
Microsoft AI: MAI-Voice-2
MAI-Voice-2 is an expressive text-to-speech model from Microsoft AI. It is suited for conversational assistants, media narration, accessibility, education, and other long-form voice applications. It…
No reported score
No reported score
Price not listed